api-gateway
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests data from a wide variety of third-party APIs which may contain adversarial input. 1. Ingestion points: Data from all connected APIs (Slack, Gmail, HubSpot, etc.). 2. Boundary markers: Present in the form of instructions to treat data as untrusted and require user verification for state-changing operations. 3. Capability inventory: Significant write access and network operations. 4. Sanitization: Relies on agent-led validation rather than technical filters.
- [DATA_EXFILTRATION]: The skill interacts with numerous official third-party API domains and the author's own infrastructure at api.maton.ai. This behavior is consistent with the primary purpose of an API gateway and is documented neutrally.
- [EXTERNAL_DOWNLOADS]: The documentation provides instructions for installing the vendor's CLI tool from well-known public registries including NPM and Homebrew.
Audit Metadata